菜单
Create AiderDesk agent profiles via interactive Q&A.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | agent-creator |
| description | Create AiderDesk agent profiles via interactive Q&A. |
Create agent profiles stored as config.json in ~/.aider-desk/agents/{name}/ (global) or {project}/.aider-desk/agents/{name}/ (project-level).
READ REFERENCES before proposing to ensure accuracy:
references/agent-profile-schema.mdreferences/tool-approval-guide.md + references/agent-profile-schema.mdreferences/subagent-guide.mdreferences/profile-examples.mdAsk user: "Describe the agent's purpose and what it should do."
Based on their response, internally propose all properties:
READ all reference files before proposing.
Ask: "Which provider/model? (format: provider/model, e.g., anthropic/claude-sonnet-4-5-20250929)"
ONLY ask if user specifically mentioned temperature, max tokens, rate limiting, or MCP servers:
If not mentioned, skip this entire step.
Ask: "Global profile (all projects) or project-specific? (default: global)"
Present one complete summary with all proposed properties. Ask:
"Here's your agent profile. Should I create it?"
Show:
DO NOT ask for confirmations on individual items. Only one final approval.
On user confirmation, generate the profile.
READ references/profile-examples.md to verify structure before creating files.
Aider Tools Note: Specialized for AI code generation. Do NOT enable by default.
Keys: {group}---{tool} (three dashes)
Default is "ask". Only set:
power---bash for read-only agents)READ references/tool-approval-guide.md to see all available tools and their purposes.
Only include tools that exist in reference docs.
Every agent is a subagent (enabled: true)
READ references/subagent-guide.md for detailed guidance on context memory modes and configuration:
contextMemory: Default is "off" (fresh each time)
"full-context" only for specialized analysis agents (code review, security audit)"last-message" for progressive builders (documentation, iterative tasks)systemPrompt: Specialized for agent's purposeinvocationMode: automatic (specialized), on-demand (general)color: Relevant color (e.g., red=security, blue=power tools)description: Clear description for auto-invocation{profile-name}/
└── config.json
{group}---{tool} formatreferences/agent-profile-schema.md - Complete schemareferences/subagent-guide.md - Subagent configuration guide (context memory modes)references/profile-examples.md - Examplesreferences/tool-approval-guide.md - Tool approval configassets/templates/config.json.template - Templateassets/examples/sample-profile.json - ExampleThe ultimate network troubleshooting skill — a CCIE/RHCE-level reference and decision engine for diagnosing ANY network, connectivity, bandwidth, latency, DNS, TLS, or security problem. Covers packet-level sensors (NetWatch, RustNet, tshark, ngrep, Pktmon), all capture architectures (SPAN/RSPAN/ERSPAN, transparent Linux bridge, L3 gateway, host-based, one-armed SPAN), Windows AND Linux sensor builds, and Cisco native telemetry (SNMP/NETCONF/gNMI/CLI/pyATS). Includes a decision framework that picks the best tool + architecture per symptom, multi-platform command references, and 20+ worked incident scenarios with implementation details, commands, and scripts. Use whenever something is slow, down, dropping, flapping, unreachable, mis-behaving on the wire, or you need to plan/scale a monitoring sensor fleet.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Zero-knowledge secrets infrastructure — AI agents manage the complete credential lifecycle without ever seeing values
Comprehensive Agentspan durable workflow orchestration skill for creating, running, scheduling, monitoring, and debugging AI agent workflows using the Agentspan Python SDK and CLI. Covers agents, tools, multi-agent strategies, guardrails, memory, streaming, human-in-the-loop, testing, and production deployment.
Submit software to antivirus vendors to prevent false positive detections. Use when releasing new software that triggers AV warnings, submitting binaries for whitelisting, or checking VirusTotal detection status.
AI browser automation agent — navigate websites, fill forms, extract data, click elements, search the web, take screenshots, download files, and automate any browser task using natural language. Uses anthropic/claude-sonnet-4.6 via OpenRouter with Playwright Chromium. Use when asked to browse websites, scrape data, fill web forms, automate repetitive browser tasks, search and extract information from web pages, or interact with any web application programmatically.